In this paper, we present KoCoNovel, a novel character coreference dataset derived from Korean literary texts, complete with detailed annotation guidelines. Comprising 178K tokens from 50 modern and contemporary novels, KoCoNovel stands as one of the largest public coreference resolution corpora in Korean, and the first to be based on literary texts. KoCoNovel offers four distinct versions to accommodate a wide range of literary coreference analysis needs. These versions are designed to support perspectives of the omniscient author or readers, and to manage multiple entities as either separate or overlapping, thereby broadening its applicability. One of KoCoNovel's distinctive features is that 24% of all character mentions are single common nouns, lacking possessive markers or articles. This feature is particularly influenced by the nuances of Korean address term culture, which favors the use of terms denoting social relationships and kinship over personal names. In experiments with a BERT-based coreference model, we observe notable performance enhancements with KoCoNovel in character coreference tasks within literary texts, compared to a larger non-literary coreference dataset. Such findings underscore KoCoNovel's potential to significantly enhance coreference resolution models through the integration of Korean cultural and linguistic dynamics.
All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR model over another is due to the choice of language model or other factors, such as the task-specific architecture, is difficult or impossible to determine due to lack of a standardized experimental setup. To resolve this ambiguity, we systematically evaluate five CR models and control for certain design decisions including the pretrained language model used by each. When controlling for language model size, encoder-based CR models outperform more recent decoder-based models in terms of both accuracy and inference speed. Surprisingly, among encoder-based CR models, more recent models are not always more accurate, and the oldest CR model that we test generalizes the best to out-of-domain textual genres. We conclude that controlling for the choice of language model reduces most, but not all, of the increase in F1 score reported in the past five years.
Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., rationales) within the ECR task. Leveraging the debiasing capability of counterfactual data augmentation, we develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop. This method is specialized for pairwise input in the ECR system, where we conduct direct interventions on triggers and context to mitigate the spurious association while emphasizing the causation. Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.
Singleton mentions, i.e.~entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. However previous attempts to incorporate their detection in end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention spans in the OntoNotes benchmark. This paper addresses this limitation by combining predicted mentions from existing nested NER systems and features derived from OntoNotes syntax trees. With this approach, we create a near approximation of the OntoNotes dataset with all singleton mentions, achieving ~94% recall on a sample of gold singletons. We then propose a two-step neural mention and coreference resolution system, named SPLICE, and compare its performance to the end-to-end approach in two scenarios: the OntoNotes test set and the out-of-domain (OOD) OntoGUM corpus. Results indicate that reconstructed singleton training yields results comparable to end-to-end systems for OntoNotes, while improving OOD stability (+1.1 avg. F1). We conduct error analysis for mention detection and delve into its impact on coreference clustering, revealing that precision improvements deliver more substantial benefits than increases in recall for resolving coreference chains.
Understanding social interactions involving both verbal and non-verbal cues is essential for effectively interpreting social situations. However, most prior works on multimodal social cues focus predominantly on single-person behaviors or rely on holistic visual representations that are not aligned to utterances in multi-party environments. Consequently, they are limited in modeling the intricate dynamics of multi-party interactions. In this paper, we introduce three new challenging tasks to model the fine-grained dynamics between multiple people: speaking target identification, pronoun coreference resolution, and mentioned player prediction. We contribute extensive data annotations to curate these new challenges in social deduction game settings. Furthermore, we propose a novel multimodal baseline that leverages densely aligned language-visual representations by synchronizing visual features with their corresponding utterances. This facilitates concurrently capturing verbal and non-verbal cues pertinent to social reasoning. Experiments demonstrate the effectiveness of the proposed approach with densely aligned multimodal representations in modeling fine-grained social interactions. Project website: https://sangmin-git.github.io/projects/MMSI.
Coreference resolution involves the task of identifying text spans within a discourse that pertain to the same real-world entity. While this task has been extensively explored in the English language, there has been a notable scarcity of publicly accessible resources and models for coreference resolution in South Asian languages. We introduce a Translated dataset for Multilingual Coreference Resolution (TransMuCoRes) in 31 South Asian languages using off-the-shelf tools for translation and word-alignment. Nearly all of the predicted translations successfully pass a sanity check, and 75% of English references align with their predicted translations. Using multilingual encoders, two off-the-shelf coreference resolution models were trained on a concatenation of TransMuCoRes and a Hindi coreference resolution dataset with manual annotations. The best performing model achieved a score of 64 and 68 for LEA F1 and CoNLL F1, respectively, on our test-split of Hindi golden set. This study is the first to evaluate an end-to-end coreference resolution model on a Hindi golden set. Furthermore, this work underscores the limitations of current coreference evaluation metrics when applied to datasets with split antecedents, advocating for the development of more suitable evaluation metrics.
While Large Language Models (LLMs) excel at the Winograd Schema Challenge (WSC), a coreference resolution task testing common-sense reasoning through pronoun disambiguation, they struggle with instances that feature minor alterations or rewording. To address this, we introduce EvoGrad, an open-source platform that harnesses a human-in-the-loop approach to create a dynamic dataset tailored to such altered WSC instances. Leveraging ChatGPT's capabilities, we expand our task instances from 182 to 3,691, setting a new benchmark for diverse common-sense reasoning datasets. Additionally, we introduce the error depth metric, assessing model stability in dynamic tasks. Our results emphasize the challenge posed by EvoGrad: Even the best performing LLM, GPT-3.5, achieves an accuracy of 65.0% with an average error depth of 7.2, a stark contrast to human performance of 92. 8% accuracy without perturbation errors. This highlights ongoing model limitations and the value of dynamic datasets in uncovering them.
As NLP models become increasingly capable of understanding documents in terms of coherent entities rather than strings, obtaining the most salient entities for each document is not only an important end task in itself but also vital for Information Retrieval (IR) and other downstream applications such as controllable summarization. In this paper, we present and evaluate GUMsley, the first entity salience dataset covering all named and non-named salient entities for 12 genres of English text, aligned with entity types, Wikification links and full coreference resolution annotations. We promote a strict definition of salience using human summaries and demonstrate high inter-annotator agreement for salience based on whether a source entity is mentioned in the summary. Our evaluation shows poor performance by pre-trained SOTA summarization models and zero-shot LLM prompting in capturing salient entities in generated summaries. We also show that predicting or providing salient entities to several model architectures enhances performance and helps derive higher-quality summaries by alleviating the entity hallucination problem in existing abstractive summarization.
The automatic transformation of verbose, natural language descriptions into structured process models remains a challenge of significant complexity - This paper introduces a contemporary solution, where central to our approach, is the use of dependency parsing and Named Entity Recognition (NER) for extracting key elements from textual descriptions. Additionally, we utilize Subject-Verb-Object (SVO) constructs for identifying action relationships and integrate semantic analysis tools, including WordNet, for enriched contextual understanding. A novel aspect of our system is the application of neural coreference resolution, integrated with the SpaCy framework, enhancing the precision of entity linkage and anaphoric references. Furthermore, the system adeptly handles data transformation and visualization, converting extracted information into BPMN (Business Process Model and Notation) diagrams. This methodology not only streamlines the process of capturing and representing business workflows but also significantly reduces the manual effort and potential for error inherent in traditional modeling approaches.
Guided by grammatical structure, words compose to form sentences, and guided by discourse structure, sentences compose to form dialogues and documents. The compositional aspect of sentence and discourse units is often overlooked by machine learning algorithms. A recent initiative called Quantum Natural Language Processing (QNLP) learns word meanings as points in a Hilbert space and acts on them via a translation of grammatical structure into Parametrised Quantum Circuits (PQCs). Previous work extended the QNLP translation to discourse structure using points in a closure of Hilbert spaces. In this paper, we evaluate this translation on a Winograd-style pronoun resolution task. We train a Variational Quantum Classifier (VQC) for binary classification and implement an end-to-end pronoun resolution system. The simulations executed on IBMQ software converged with an F1 score of 87.20%. The model outperformed two out of three classical coreference resolution systems and neared state-of-the-art SpanBERT. A mixed quantum-classical model yet improved these results with an F1 score increase of around 6%.
There is a significant disconnect between linguistic theory and modern NLP practice, which relies heavily on inscrutable black-box architectures. DisCoCirc is a newly proposed model for meaning that aims to bridge this divide, by providing neuro-symbolic models that incorporate linguistic structure. DisCoCirc represents natural language text as a `circuit' that captures the core semantic information of the text. These circuits can then be interpreted as modular machine learning models. Additionally, DisCoCirc fulfils another major aim of providing an NLP model that can be implemented on near-term quantum computers. In this paper we describe a software pipeline that converts English text to its DisCoCirc representation. The pipeline achieves coverage over a large fragment of the English language. It relies on Combinatory Categorial Grammar (CCG) parses of the input text as well as coreference resolution information. This semantic and syntactic information is used in several steps to convert the text into a simply-typed $\lambda$-calculus term, and then into a circuit diagram. This pipeline will enable the application of the DisCoCirc framework to NLP tasks, using both classical and quantum approaches.
Instruction-following language models demand robust methodologies for information retrieval to augment instructions for question-answering applications. A primary challenge is the resolution of coreferences in the context of chunking strategies for long documents. The critical barrier to experimentation of handling coreferences is a lack of open source datasets, specifically in question-answering tasks that require coreference resolution. In this work we present our Coreference Resolution in Question-Answering (CRaQAn) dataset, an open-source dataset that caters to the nuanced information retrieval requirements of coreference resolution in question-answering tasks by providing over 250 question-answer pairs containing coreferences. To develop this dataset, we developed a novel approach for creating high-quality datasets using an instruction-following model (GPT-4) and a Recursive Criticism and Improvement Loop.
We present CorPipe, the winning entry to the CRAC 2023 Shared Task on Multilingual Coreference Resolution. Our system is an improved version of our earlier multilingual coreference pipeline, and it surpasses other participants by a large margin of 4.5 percent points. CorPipe first performs mention detection, followed by coreference linking via an antecedent-maximization approach on the retrieved spans. Both tasks are trained jointly on all available corpora using a shared pretrained language model. Our main improvements comprise inputs larger than 512 subwords and changing the mention decoding to support ensembling. The source code is available at https://github.com/ufal/crac2023-corpipe.
Various NLP tasks require a complex hierarchical structure over nodes, where each node is a cluster of items. Examples include generating entailment graphs, hierarchical cross-document coreference resolution, annotating event and subevent relations, etc. To enable efficient annotation of such hierarchical structures, we release CHAMP, an open source tool allowing to incrementally construct both clusters and hierarchy simultaneously over any type of texts. This incremental approach significantly reduces annotation time compared to the common pairwise annotation approach and also guarantees maintaining transitivity at the cluster and hierarchy levels. Furthermore, CHAMP includes a consolidation mode, where an adjudicator can easily compare multiple cluster hierarchy annotations and resolve disagreements.
Multilingual coreference resolution (MCR) has been a long-standing and challenging task. With the newly proposed multilingual coreference dataset, CorefUD (Nedoluzhko et al., 2022), we conduct an investigation into the task by using its harmonized universal morphosyntactic and coreference annotations. First, we study coreference by examining the ground truth data at different linguistic levels, namely mention, entity and document levels, and across different genres, to gain insights into the characteristics of coreference across multiple languages. Second, we perform an error analysis of the most challenging cases that the SotA system fails to resolve in the CRAC 2022 shared task using the universal annotations. Last, based on this analysis, we extract features from universal morphosyntactic annotations and integrate these features into a baseline system to assess their potential benefits for the MCR task. Our results show that our best configuration of features improves the baseline by 0.9% F1 score.
Adult content detection still poses a great challenge for automation. Existing classifiers primarily focus on distinguishing between erotic and non-erotic texts. However, they often need more nuance in assessing the potential harm. Unfortunately, the content of this nature falls beyond the reach of generative models due to its potentially harmful nature. Ethical restrictions prohibit large language models (LLMs) from analyzing and classifying harmful erotics, let alone generating them to create synthetic datasets for other neural models. In such instances where data is scarce and challenging, a thorough analysis of the structure of such texts rather than a large model may offer a viable solution. Especially given that harmful erotic narratives, despite appearing similar to harmless ones, usually reveal their harmful nature first through contextual information hidden in the non-sexual parts of the narrative. This paper introduces a hybrid neural and rule-based context-aware system that leverages coreference resolution to identify harmful contextual cues in erotic content. Collaborating with professional moderators, we compiled a dataset and developed a classifier capable of distinguishing harmful from non-harmful erotic content. Our hybrid model, tested on Polish text, demonstrates a promising accuracy of 84% and a recall of 80%. Models based on RoBERTa and Longformer without explicit usage of coreference chains achieved significantly weaker results, underscoring the importance of coreference resolution in detecting such nuanced content as harmful erotics. This approach also offers the potential for enhanced visual explainability, supporting moderators in evaluating predictions and taking necessary actions to address harmful content.
Existing works on coreference resolution suggest that task-specific models are necessary to achieve state-of-the-art performance. In this work, we present compelling evidence that such models are not necessary. We finetune a pretrained seq2seq transformer to map an input document to a tagged sequence encoding the coreference annotation. Despite the extreme simplicity, our model outperforms or closely matches the best coreference systems in the literature on an array of datasets. We also propose an especially simple seq2seq approach that generates only tagged spans rather than the spans interleaved with the original text. Our analysis shows that the model size, the amount of supervision, and the choice of sequence representations are key factors in performance.
Event coreference resolution (ECR) aims to group event mentions referring to the same real-world event into clusters. Most previous studies adopt the "encoding first, then scoring" framework, making the coreference judgment rely on event encoding. Furthermore, current methods struggle to leverage human-summarized ECR rules, e.g., coreferential events should have the same event type, to guide the model. To address these two issues, we propose a prompt-based approach, CorefPrompt, to transform ECR into a cloze-style MLM (masked language model) task. This allows for simultaneous event modeling and coreference discrimination within a single template, with a fully shared context. In addition, we introduce two auxiliary prompt tasks, event-type compatibility and argument compatibility, to explicitly demonstrate the reasoning process of ECR, which helps the model make final predictions. Experimental results show that our method CorefPrompt performs well in a state-of-the-art (SOTA) benchmark.
In this paper, we study multimodal coreference resolution, specifically where a longer descriptive text, i.e., a narration is paired with an image. This poses significant challenges due to fine-grained image-text alignment, inherent ambiguity present in narrative language, and unavailability of large annotated training sets. To tackle these challenges, we present a data efficient semi-supervised approach that utilizes image-narration pairs to resolve coreferences and narrative grounding in a multimodal context. Our approach incorporates losses for both labeled and unlabeled data within a cross-modal framework. Our evaluation shows that the proposed approach outperforms strong baselines both quantitatively and qualitatively, for the tasks of coreference resolution and narrative grounding.
We introduce a novel and efficient method for Event Coreference Resolution (ECR) applied to a lower-resourced language domain. By framing ECR as a graph reconstruction task, we are able to combine deep semantic embeddings with structural coreference chain knowledge to create a parameter-efficient family of Graph Autoencoder models (GAE). Our method significantly outperforms classical mention-pair methods on a large Dutch event coreference corpus in terms of overall score, efficiency and training speed. Additionally, we show that our models are consistently able to classify more difficult coreference links and are far more robust in low-data settings when compared to transformer-based mention-pair coreference algorithms.